© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1128
    Prev
    Next
    INDEX
    Explanations

    company or business names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥ¡åIJĮ
    -0.11
    梢
    -0.09
    ä¸ĵä¸ļ人士
    -0.09
    ipop
    -0.09
    è´§æŀ¶
    -0.09
    ä¿¡ç®±
    -0.09
    æĻļæĬ¥
    -0.08
    æĿ¾å¼Ľ
    -0.08
    æļĤç¼ĵ
    -0.08
     capable
    -0.08
    POSITIVE LOGITS
    å²Ĺä½į
    0.11
    å½ķçĶ¨
    0.10
     lÆ°Æ¡ng
    0.09
    åºĶèģĺ
    0.09
    èĸªèµĦ
    0.09
    å¾ħéģĩ
    0.09
    employ
    0.09
    æľĪèĸª
    0.09
    ä»İäºĭ
    0.08
    anter
    0.08
    Activations Density 0.176%

    No Known Activations